EdgeTrak System

People: Min Li Chandra Kambhamettu Maureen Stone Gowri Somanath

The EdgeTrak System (U.S. Copyright No. TXu 1-234-567) was developed at VIMS Lab for automatic contour tracking. It was specially developed for use on ultrasound image sequences of human tongue. The noise and unrelated high-contrast edges in ultrasound images make it very difficult to automatically detect the correct tongue surfaces. In our tracking system, a novel active contour model is developed. Unlike the classical active contour models which only use gradient of the image as the image force, the proposed model incorporates the edge gradient and intensity information in local regions around each snake element. Different from other active contour models that use homogeneity of intensity in a region as the constraint and thus are only applied to closed contours, the proposed model applies local region information to open contours and can be used to track partial tongue surfaces in ultrasound images. The contour orientation is also taken into account so that any unnecessary edges in ultrasound images will be discarded.

The system is being used by several institutions such as: Dental School, University of Maryland (Dr. Maureen Stone); Department of Linguistics, New York University (Dr. Lisa Davidson); and Department of Linguistics, Cornell University (Dr. Amanda Miller-Ockhuizen).

Code

The EdgeTrak package with source code and documents can be downloaded from here. Use of any part of the package must cite the paper listed in the Reference. Please direct any questions to Chandra Kambhamettu.

Reference

Min Li, Chandra Kambhamettu and Maureen Stone , "Automatic Contour Tracking in Ultrasound Images", International Journal of Clinical Linguistics and Phonetics., 19 (6-7): 545-554, 2005.